Tong Zhang
Talk: Reinforcement Learning for Foundation Models: Theory, Algorithms, and Applications
This talk provides an overview of our group’s research on reinforcement learning (RL) for foundation models. I will discuss how RL principles can improve the training, alignment, and capabilities of large language models, highlighting the theoretical foundations, theoretically motivated algorithms, and their applications to foundation model training, digital assistants, embodied agents, and scientific discovery. I will also outline our ongoing efforts to build more capable, interactive, and reliable agents across diverse domains using RL.
BIO:
Tong Zhang is a professor in the Computer Science department at the University of Illinois Urbana Champaign. He is a fellow of the IEEE, American Statistical Association, and Institute of Mathematical Statistics. His research interests include machine learning theory, algorithms, and applications. Tong Zhang has served as the chair or area chair in major machine learning conferences such as NeurIPS, ICML, and COLT, and has also served on the editorial boards of leading machine learning journals such as PAMI, JMLR, and the Machine Learning Journal.